← Back to community benchmarks

gemma4-26b-a4b-it

M4 Max (32c) · 36 GB · 6bit · 2026-04-29
Performance
16k
tokens
1,069
PP tok/s
39.8
TG tok/s
15322
TTFT (ms)
20.9
Peak mem (GB)
Hardware
Chip M4 Max (32c)
Memory 36 GB
GPU Cores 32
Software
oMLX v0.3.6
macOS macOS 15.7.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 974.7 68.2 20.0 GB view
4k 1,104 64.2 20.4 GB view
8k 1,115 51.2 20.5 GB view
16k 1,069 39.8 20.9 GB current
32k 968.4 27.2 21.7 GB view
Batching Results
Batch Size TG tok/s Speedup
68.2 1.00×
135.1 1.98×
273.2 4.01×